search

HighwayWu / ImageInpainting

36 stars 8 forks source link

no backpropagation for netLBP? #5

Closed vinits5 closed 3 years ago

vinits5 commented 3 years ago

While going through the code, I found that netLBP's parameters are not getting updated as the optimizerLBP.step() function is not called anywhere in model.py file.

https://github.com/HighwayWu/ImageInpainting/blob/master/model.py#L268 I believe that the above link indicates the function that optimizes parameters of netG, netD, netD2 but it does not update netLBP. Can you please point me to the correct location where the optimizer for LBP is calling the step function? Thank you.

HighwayWu commented 3 years ago

Hi, Vinits.

Actually, this script is for training the second stage of the model, i.e., the image inpainting network. In this stage, I assume that the netLBP is already trained, so I remove the optimizerLBP. If you want to retrain the whole model, it would be better to train the netLBP as first; otherwise, you may add the step of optimizerLBP to form an end-to-end training.

Best, Haiwei